© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45265
    Prev
    Next
    INDEX
    Explanations

    radiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Open
    -0.08
     API
    -0.08
     disrespect
    -0.08
     lied
    -0.07
     Hotline
    -0.07
    API
    -0.07
     soup
    -0.07
     fortune
    -0.07
     IPv
    -0.07
     hotline
    -0.07
    POSITIVE LOGITS
     combine
    0.10
     combining
    0.09
    combined
    0.09
     Combining
    0.09
    combine
    0.09
    Meer
    0.09
    结合
    0.09
     gecombineerd
    0.08
     gald
    0.08
    หลัง
    0.08
    Activations Density 0.007%

    No Known Activations